Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4205 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.6081. Min Act: -0.1700
Data Index: 5601485 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.4519. Min Act: -0.1700
Data Index: 1160720 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.3894. Min Act: -0.1700
Data Index: 7977296 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.3894. Min Act: -0.1700
Data Index: 2899268 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.3581. Min Act: -0.1700
Data Index: 8083721 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.3894. Min Act: -0.1700
Data Index: 4122235 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.3581. Min Act: -0.1700
Data Index: 1125500 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.3269. Min Act: -0.1700
Data Index: 3764593 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.3269. Min Act: -0.1700
Data Index: 971336 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.2956. Min Act: -0.1700
Data Index: 5035189 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.2644. Min Act: -0.1700
Data Index: 3617710 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.3269. Min Act: -0.1700
Data Index: 1264620 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.2644. Min Act: -0.1700
Data Index: 3451974 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.2331. Min Act: -0.1700
Data Index: 8699690 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.2331. Min Act: -0.1700
Data Index: 6181605 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.2331. Min Act: -0.1700
Data Index: 7590398 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.2018. Min Act: -0.1700
Data Index: 5358736 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.2018. Min Act: -0.1700
Data Index: 1667449 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.1706. Min Act: -0.1700
Data Index: 4168918 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.2018. Min Act: -0.1700
Data Index: 4575418 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19